AB-730 Questions and Answers

When building a custom agent in Microsoft 365 Copilot for marketing use cases, the required capabilities must align with the intended outputs. Marketing collateral includes written copy as well as visual assets such as logos and artwork. According to Microsoft AI Business Professional documentation, generative AI solutions that produce visual creative assets require integrated image generation capabilities powered by multimodal AI models.

Option C is correct because an image generator enables the agent to create visual marketing materials such as logos, artwork, and design elements. While templates and suggested prompts can improve usability and consistency, they do not provide the underlying capability to generate images. A code interpreter is designed for data analysis, calculations, or technical scripting tasks and is not relevant to creative marketing asset production.

Therefore, to fulfill the requirement of producing both textual and visual marketing collateral, the most essential addition to the custom agent is an image generator.

When you use Microsoft 365 Copilot Chat without a Microsoft 365 Copilot license, Copilot Chat operates in a “general” mode rather than a Microsoft Graph-grounded work mode. In this configuration, Copilot does not have the entitlement to access and reason over your organization’s protected Microsoft 365 content (such as SharePoint sites, OneDrive files, Outlook mail, Teams messages, or other tenant resources). It also does not connect directly to your organization’s internal databases unless separate, explicitly configured integrations exist.

Instead, Copilot relies on three primary sources to generate a response: (1) the prompt context you provide in the current request (what you ask, plus any text you paste), (2) the conversation history within the current chat thread to maintain continuity, and (3) internet search data (when web grounding is available) to supplement general knowledge with up-to-date public information.

Therefore, the correct selections are C (prompt context), E (internet search data), and F (conversation history) , while organizational Microsoft 365 data and Teams chat data are not used without the Copilot license.

Microsoft 365 Copilot integrates with Microsoft Search to help users discover relevant content across their organization’s Microsoft 365 data estate, including SharePoint, OneDrive, Teams, and Exchange. When the objective is to determine whether similar training plans already exist, the appropriate action is to perform a search across organizational content.

Using Search allows Copilot to query indexed enterprise documents and return files, plans, or related materials that the user has permission to access. This supports content reuse, avoids duplication of work, and aligns with Microsoft’s guidance on leveraging organizational knowledge efficiently.

Designer is focused on visual content creation, Apps provides access to Microsoft 365 applications, and Pages is used for creating and organizing content within Copilot. None of these options are intended for discovering existing documents across the tenant.

Therefore, to identify similar existing training plans within your organization, the correct tool to use in Copilot is Search.

==================================================

In the Microsoft 365 Copilot app, the Conversations list can display status indicators next to individual conversation titles. In the exhibit, the Standings conversation has a distinct indicator (a green badge) shown to the right of the conversation name. This badge is used to signal that the conversation includes a verified response.

A verified response indicator is intended to help users quickly recognize outputs that were produced with stronger grounding and traceability—for example, responses that include supporting citations or references that can be reviewed for accuracy. This aligns with Microsoft’s guidance on improving trust in AI output by making source-backed or verification-supported responses easier to identify and validate.

The other options do not match the indicator shown. Conversations that are shared or added to notebooks typically use different share/notebook iconography, and scheduled prompts are represented with scheduling-related indicators rather than a verification badge. “Anonymous data” is not something Copilot marks at the conversation level in this manner.

Therefore, the best inference is that the Standings conversation contains a verified response.

When you add a file to a Microsoft 365 Copilot notebook from a Microsoft SharePoint site , you are referencing a document that is stored and managed within Microsoft 365. SharePoint maintains a single authoritative file that can be updated over time (with version history behind the scenes). Copilot notebooks that reference SharePoint content are designed to stay grounded in the current version of that cloud-hosted document, subject to your permissions.

Because Process.docx is stored in SharePoint, the notebook reference points to the SharePoint document itself rather than a static local snapshot. When another user updates the document in SharePoint, the “latest” content becomes the current version available at that location. When you chat in the notebook, Copilot will use the file as it exists now in SharePoint, which means it will reference the most recent version.

Option A would be typical only if you attached a local file upload (a static copy) rather than a SharePoint-hosted file. Option C is incorrect because Copilot uses the current file at the referenced location, not multiple historical versions simultaneously.

Therefore, the chat will reference the most recent version of Process.docx .

Prompt injection is a generative AI security risk where an attacker inserts instructions (often hidden in text, documents, webpages, or user inputs) to override or manipulate the assistant’s intended behavior. This can lead to unintended actions such as ignoring policy controls, producing unsafe outputs, or attempting to reveal sensitive information. Because generative AI systems follow natural-language instructions, they can be socially engineered to prioritize malicious content unless safeguards are in place. This is why prompt injection can cause data exposure (for example, attempting to extract confidential content from grounded sources) and can also embed harmful instructions that redirect the model’s behavior. In enterprise settings like Microsoft 365 Copilot, mitigations include grounding boundaries, permission trimming, content filtering, and instruction hierarchy (system policies over user instructions). From a business governance perspective, users should treat untrusted inputs (emails, documents, web text) as potentially hostile and apply least-privilege access and validation when using AI outputs in decision-making.

Microsoft 365 Copilot in Teams is designed to provide real-time meeting assistance, including summarizing discussions, identifying key decisions, and highlighting action items. When joining a meeting late, the most efficient and immediate method to catch up is to directly prompt Copilot within the Teams meeting experience.

Option A is the best answer because Copilot in Teams can summarize what has occurred so far during the live meeting. It leverages the meeting transcript, speaker attribution, and contextual signals to generate a concise, structured summary in real time. This minimizes delay and provides actionable insights instantly.

Reading the transcript (Option B) would require manual review and is not the fastest method. Intelligent recap (Option D) is typically available after the meeting concludes and processes recording data. Asking Copilot from the separate Microsoft 365 Copilot app (Option C) may not provide immediate, in-meeting contextual awareness.

Therefore, the fastest and most effective approach is to ask Copilot in Teams to summarize what you missed.

Microsoft 365 Copilot can use Microsoft Graph-grounded data (based on the user’s permissions) to help users work with Microsoft 365 content. This includes surfacing and summarizing information from Teams chats , so statement 1 is true. Copilot can also summarize and generate content related to Teams meetings (for example, meeting recap details, key discussion points, and follow-up actions when meeting artifacts such as transcript/notes are available), and it can answer questions and draft related content—so statement 3 is true.

Statement 2 is false because, while Copilot can draft emails and help prepare messages, it does not independently schedule and send emails automatically “based on conditions” as a native Copilot function. Conditional sending is typically handled through workflow automation tools (for example, Power Automate) and still requires appropriate configuration, permissions, and governance. In enterprise environments, this separation helps reduce risk by ensuring that automated outbound communication remains controlled, auditable, and compliant.

The first statement is correct because Microsoft 365 provides transparency and user control through the My Account portal, where users can review their Copilot activity history. This aligns with Microsoft’s responsible AI and data governance principles, ensuring visibility into AI interactions.

The second statement is incorrect. Deleting Copilot activity history removes stored interaction records (such as prompts and responses), but it does not automatically delete associated notebooks, documents, or pages stored in services like OneDrive or SharePoint. Those files remain governed by standard Microsoft 365 retention and lifecycle policies.

The third statement is correct because users can delete their entire Copilot activity history, including both prompts and generated responses. This reinforces enterprise-grade privacy controls and regulatory compliance requirements.

These controls demonstrate core generative AI fundamentals: transparency, user data ownership, security boundaries, and responsible lifecycle management of AI-generated interactions within Microsoft 365 environments.

When building a custom analytics agent in Microsoft 365 Copilot that must process structured data from Excel files, advanced analytical capabilities are required. According to Microsoft AI Business Professional guidance, tasks such as performing mathematical calculations, generating aggregations, creating charts, and conducting structured data analysis require programmatic execution capabilities rather than simple text generation.

A code interpreter enables the agent to run Python-based analytical operations in a secure execution environment. This allows the agent to manipulate datasets, compute totals and averages, perform grouping and filtering, and generate visualizations such as bar charts or line graphs based on the Excel data. The interpreter bridges the gap between natural language instructions and executable analytical logic.

An image generator is designed for creative visual content and is unrelated to structured data analytics. Suggested prompts and templates improve usability and consistency but do not provide computational or visualization capabilities.

Therefore, to enable mathematical operations, aggregation, data analysis, and visualization of Excel sales data, the correct component to add to the agent is a code interpreter.

Copilot in Word assists with content generation, summarization, rewriting, and structural organization. It can analyze document headings and insert a table of contents based on structured heading styles, supporting document navigation. It can also generate summaries of key points, which aligns directly with generative AI text analysis capabilities.

Custom watermark formatting and precise page margin configuration are traditional Word formatting functions and are not core generative AI capabilities of Copilot.

Therefore, the correct answers are A and C.

==================================================

When creating an agent in the Microsoft 365 Copilot app using a template, administrators or authorized users can configure specific behaviors and knowledge sources for the agent. Therefore, it is correct that you can choose which knowledge sources the agent can use. This ensures proper grounding in approved Microsoft 365 data such as SharePoint sites, OneDrive folders, or other organizational repositories. Controlling knowledge sources supports responsible AI principles, including data security, relevance, and compliance.

Agents created within Microsoft 365 are designed primarily for internal organizational use. As a result, sharing the agent with users inside the organization is supported, enabling collaboration and productivity improvements across teams.

However, sharing the agent with external users is not supported by default. External sharing would introduce security and compliance risks, so Microsoft enforces tenant-level boundaries to protect enterprise data.

These capabilities reflect best practices in managing AI prompts and agents securely within enterprise environments.

Microsoft 365 Copilot is designed to be helpful by using work context —for example, the files you have access to, recent activity, meetings, emails, and SharePoint/OneDrive content—to suggest relevant prompts and help you start tasks faster. It also uses this context to augment your prompt before it is sent to the LLM. This is the grounding approach (often described as retrieval-augmented generation): Copilot retrieves relevant organizational content you’re permitted to access and adds it as supporting context so responses are accurate and business-relevant. However, Microsoft 365 Copilot does not use your organization’s contextual data to train the underlying foundation model . That separation is critical for enterprise privacy and compliance: your prompts, responses, and tenant data are used to generate the answer for your session and permissions, but are not used to improve or retrain the base LLM. This approach supports responsible AI, protects confidential business information, and ensures outputs respect access controls.

Microsoft Purview is the correct choice because it is Microsoft’s unified compliance and data governance solution that helps organizations apply and enforce policies across Microsoft 365 content— including Copilot-related interactions where those interactions are captured in services such as Microsoft 365 audit, eDiscovery, and Purview compliance experiences. Purview supports capabilities such as data loss prevention (DLP) , retention , eDiscovery , audit , and sensitivity labeling so organizations can manage and govern data and AI-assisted content in line with regulatory and internal requirements. In contrast, Microsoft Entra ID focuses on identity and access management, Intune focuses on device and application management, and Defender for Cloud focuses on cloud security posture management. Governance policies for Copilot-generated conversations and associated compliance controls align most directly with Purview , which is designed to manage information protection and compliance across the Microsoft 365 environment.

Temporary chat in Microsoft 365 Copilot is designed for privacy-focused, non-persistent interactions. When a user initiates a temporary chat session, the conversation is not saved to Copilot chat history and is not retained for future reference within the standard conversation history interface.

Once the session ends or a new chat begins, the prompts and responses from that temporary session are deleted immediately. They are not moved to OneDrive, stored in a notebook, or retained for a delayed deletion period.

This feature supports secure and confidential usage scenarios where users may want to explore ideas, draft sensitive content, or test prompts without creating a stored record in their activity history.

From a generative AI governance perspective, this reflects Microsoft’s design principle of providing configurable persistence levels, balancing productivity with enterprise security, compliance, and user privacy controls.

Use the Analyst agent for Prompt 1 because it is optimized for structured data work: consolidating worksheets, performing calculations, sentiment breakdowns by category (product line), and producing visualizations. These tasks align with analysis-style workflows where quantitative processing and charting are required.

Use the Researcher agent for Prompt 2 because it is designed to synthesize information from multiple sources, including SharePoint content plus web grounding , and to produce a well-structured brief with citations . Researcher is best when you need evidence-backed insights, reputable sourcing, and an organized narrative with risks and gaps.

Use Chat for Prompt 3 because the goal is drafting a refined executive email based on an attached document with tone control and communication standards. Chat excels at business writing, rewriting, tone adjustment, and producing polished communications without needing the deeper research workflow or heavy data analytics specialization.

Microsoft 365 Copilot provides structured ways to persist and reuse knowledge sources to avoid repeatedly uploading the same files.

Creating a notebook that references the five files (Option B) allows those documents to remain attached within a persistent workspace. Copilot can then consistently ground responses in those files without re-uploading them for every conversation.

Creating an agent with a defined knowledge source (Option D) also provides a reusable solution. By configuring the five files as part of the agent’s knowledge base, the agent can automatically reference them in future interactions.

Saving a prompt does not persist file attachments. Fine-tuning models is not part of standard Microsoft 365 Copilot user workflows. Uploading a ZIP file does not improve reference management and may reduce accessibility of individual documents.

Therefore, the correct solutions are to create a notebook that references the files and to create an agent with a knowledge source.

Microsoft 365 Copilot agents operate within the security, compliance, and identity boundaries of a Microsoft 365 tenant. Custom agents created in the Microsoft 365 Copilot app are governed by organizational policies, role-based access control, and Microsoft Entra ID authentication.

According to Microsoft AI Business Professional guidance, Copilot agents are designed for enterprise use and are shared within the organization unless administrators configure broader sharing capabilities. External sharing with personal Microsoft accounts or arbitrary email addresses is not supported by default due to security, data protection, and compliance requirements.

Because the agent in this scenario interacts with organizational data such as client emails, project milestones, and internal reports, access must remain restricted to authenticated users within the same tenant. This ensures that sensitive business information remains protected and that data access respects existing permissions.

Therefore, the agent can be shared only with people in your organization, making option D the correct answer.